Intelligent machines of the future may need to sleep as much as we do.
States that resemble sleep-like cycles in simulated neural networks quell the instability that comes with uninterrupted self-learning in artificial analogs of brains
No one can say whether androids will dream of electric sheep, but they will almost certainly need periods of rest that offer benefits similar to those that sleep provides to living brains, according to new research from Los Alamos National Laboratory.
“We study spiking neural networks, which are systems that learn much as living brains do,” said Los Alamos National Laboratory computer scientist Yijing Watkins. “We were fascinated by the prospect of training a neuromorphic processor in a manner analogous to how humans and other biological systems learn from their environment during childhood development.”
It was as though we were giving the neural networks the equivalent of a good night’s rest
Watkins and her research team found that the network simulations became unstable after continuous periods of unsupervised learning. When they exposed the networks to states that are analogous to the waves that living brains experience during sleep, stability was restored. “It was as though we were giving the neural networks the equivalent of a good night’s rest,” said Watkins.
The discovery came about as the research team worked to develop neural networks that closely approximate how humans and other biological systems learn to see. The group initially struggled with stabilizing simulated neural networks undergoing unsupervised dictionary training, which involves classifying objects without having prior examples to compare them to.
“The issue of how to keep learning systems from becoming unstable really only arises when attempting to utilize biologically realistic, spiking neuromorphic processors or when trying to understand biology itself,” said Los Alamos computer scientist and study coauthor Garrett Kenyon. “The vast majority of machine learning, deep learning, and AI researchers never encounter this issue because in the very artificial systems they study they have the luxury of performing global mathematical operations that have the effect of regulating the overall dynamical gain of the system.”
The researchers characterize the decision to expose the networks to an artificial analog of sleep as nearly a last ditch effort to stabilize them. They experimented with various types of noise, roughly comparable to the static you might encounter between stations while tuning a radio. The best results came when they used waves of so-called Gaussian noise, which includes a wide range of frequencies and amplitudes. They hypothesize that the noise mimics the input received by biological neurons during slow-wave sleep. The results suggest that slow-wave sleep may act, in part, to ensure that cortical neurons maintain their stability and do not hallucinate.
The groups’ next goal is to implement their algorithm on Intel’s Loihi neuromorphic chip. They hope allowing Loihi to sleep from time to time will enable it to stably process information from a silicon retina camera in real time. If the findings confirm the need for sleep in artificial brains, we can probably expect the same to be true of androids and other intelligent machines that may come about in the future.
The Latest Updates from Bing News & Google News
Go deeper with Bing News on:
Neuromorphic processor
- Neuromorphic Chip Market Size To Touch $2734.8 Million By 2031 Driven By Industrial Adoption And Big Data Analysis
Neuromorphic chips offer a revolutionary approach to computing by mimicking the human brain's structure and function. These chips leverage spiking neural networks (SNNs) that emulate the biological ...
- SpiNNcloud Systems Unveils Innovative Neuromorphic Supercomputer SpiNNaker2
SpiNNcloud System has revealed their revolutionary SpiNNaker2 platform which is a new hybrid AI supercomputer based on principles from the human brain as a next generation machine. Developed by Steve ...
- SpiNNcloud Systems unveils Arm-based 'neuromorphic supercomputer'
Brain-inspired chip folks set to show off hardware at ISC next week SpiNNcloud Systems says it is making commercially available a hybrid AI high performance computer system based on an architecture ...
- Neuromorphic supercomputer SpiNNaker 2 can be rented in the cloud
SpiNNcloud Systems offers access to up to 656,640 economical CPU cores with accelerators that calculate up to 0.3 quintillion operations per second.
- SpiNNcloud Systems launches SpiNNaker2, the first commercial neuromorphic supercomputer
German neuromorphic supercomputing company SpiNNcloud Systems GmbH today announced the first commercially available neuromorphic supercomputer with the launch of its SpiNNaker2 pl ...
Go deeper with Google Headlines on:
Neuromorphic processor
[google_news title=”” keyword=”neuromorphic processor” num_posts=”5″ blurb_length=”0″ show_thumb=”left”]
Go deeper with Bing News on:
Artificial brains
- Scientists Imaged and Mapped a Tiny Piece of Human Brain. Here’s What They Found
With the help of an artificial intelligence algorithm, the researchers produced 1.4 million gigabytes of data from a cubic millimeter of brain tissue ...
- Researchers create AI model to understand how brain activity relates to illness
A team of researchers at Baylor College of Medicine and Yale University incorporated generative artificial intelligence (AI) to create a foundational model for brain activity. The Brain Language Model ...
- Largest-ever 3D map of human brain created by Harvard and Google
Harvard and Google created the largest 3D map of the human brain, mapping 57,000 cells and 150 million synapses in a tiny fragment.
- Consciousness Could Hinge on How Your Brain Handles Metals, Scientists Say
“Fusing” these two neuroscience theories —the Global Neuronal Network and the Tripartite Mechanism of Memory—forms the basis of this new paradigm. The researchers state that this combined theory ...
- Bored with mimicking the human brain, Google's AI division is now mapping it
So little is known about the brain and AI is being used to help. Google's AI tools created a complex brain map for scientists to study. Using these maps, it might be possible to understand why brain ...
Go deeper with Google Headlines on:
Artificial brains
[google_news title=”” keyword=”artificial brains” num_posts=”5″ blurb_length=”0″ show_thumb=”left”]